Correction: Identifying patients at risk for severe exacerbations of asthma: development and external validation of a multivariable prediction model

ObjectiveIdentification of older patients at risk, among those accessing the emergency department (ED), may support clinical decision-making. To this purpose, we developed and validated the Dynamic Silver Code (DSC), a score based on real-time linkage of administrative data.Design and settingThe ‘Silver Code National Project (SCNP)’, a non-concurrent cohort study, was used for retrospective development and internal validation of the DSC. External validation was obtained in the ‘Anziani in DEA (AIDEA)’ concurrent cohort study, where the DSC was generated by the software routinely used in the ED.ParticipantsThe SCNP contained 281 321 records of 180 079 residents aged 75+ years from Tuscany and Lazio, Italy, admitted via the ED to Internal Medicine or Geriatrics units. The AIDEA study enrolled 4425 subjects aged 75+ years (5217 records) accessing two EDs in the area of Florence, Italy.InterventionsNone.Outcome measuresPrimary outcome: 1-year mortality. Secondary outcomes: 7 and 30-day mortality and 1-year recurrent ED visits.ResultsAdvancing age, male gender, previous hospital admission, discharge diagnosis, time from discharge and polypharmacy predicted 1-year mortality and contributed to the DSC in the development subsample of the SCNP cohort. Based on score quartiles, participants were classified into low, medium, high and very high-risk classes. In the SCNP validation sample, mortality increased progressively from 144 to 367 per 1000 person-years, across DSC classes, with HR (95% CI) of 1.92 (1.85 to 1.99), 2.71 (2.61 to 2.81) and 5.40 (5.21 to 5.59) in class II, III and IV, respectively versus class I (p<0.001). Findings were similar in AIDEA, where the DSC predicted also recurrent ED visits in 1 year. In both databases, the DSC predicted 7 and 30-day mortality.ConclusionsThe DSC, based on administrative data available in real time, predicts prognosis of older patients and might improve their management in the ED.

Download Full-text

Identifying patients at risk for future exacerbations of asthma: Development of a prediction model

10.1183/13993003.congress-2015.pa2540 ◽

2015 ◽

Cited By ~ 1

Author(s):

Rik J.B. Loymans ◽

Persijn J. Honkoop ◽

Evelien H. Termeer ◽

Helen K. Reddel ◽

Jiska B. Snoeck-Stroband ◽

...

Keyword(s):

At Risk ◽

Prediction Model ◽

Patients At Risk

Download Full-text

Prediction Model to Identify Patients at Risk of 30-Day Treatment Failure in Patients With Staphylococcus aureus Bacteremia

Open Forum Infectious Diseases ◽

10.1093/ofid/ofw172.791 ◽

2016 ◽

Vol 3 (suppl_1) ◽

Author(s):

Natasha Holmes ◽

J. Owen Robinson ◽

Sebastian Van Hal ◽

Wendy Munckhof ◽

Eugene Athan ◽

...

Keyword(s):

At Risk ◽

Staphylococcus Aureus ◽

Treatment Failure ◽

Prediction Model ◽

Day Treatment ◽

Staphylococcus Aureus Bacteremia ◽

Patients At Risk

Download Full-text

The Modified A-DIVA Scale as a Predictive Tool for Prospective Identification of Adult Patients at Risk of a Difficult Intravenous Access: A Multicenter Validation Study

Journal of Clinical Medicine ◽

10.3390/jcm8020144 ◽

2019 ◽

Vol 8 (2) ◽

pp. 144 ◽

Cited By ~ 4

Author(s):

Fredericus van Loon ◽

Loes van Hooff ◽

Hans de Boer ◽

Seppe Koopman ◽

Marc Buise ◽

...

Keyword(s):

At Risk ◽

External Validation ◽

Venous Access ◽

High Risk Group ◽

Outcome Variable ◽

Predictive Tool ◽

Intravenous Access ◽

Patients At Risk ◽

History Of ◽

Group A

Peripheral intravenous cannulation is the most common invasive hospital procedure but is associated with a high failure rate. This study aimed to improve the A-DIVA scale (Adult Difficult Intra Venous Access Scale) by external validation, to predict the likelihood of difficult intravenous access in adults. This multicenter study was carried out throughout five hospitals in the Netherlands. Adult participants were included, regardless of their indication for intravenous access, demographics, and medical history. The main outcome variable was defined as failed peripheral intravenous cannulation on the first attempt. A total of 3587 participants was included in this study. The first attempt success rate was 81%. Finally, five variables were included in the prediction model: a history of difficult intravenous cannulation, a difficult intravenous access as expected by the practitioner, the inability to detect a dilated vein by palpating and/or visualizing the extremity, and a diameter of the selected vein less than 3 millimeters. Based on a participant’s individual score on the A-DIVA scale, they were classified into either a low, moderate, or high-risk group. A higher score on the A-DIVA scale indicates a higher risk of difficult intravenous access. The five-variable additive A-DIVA scale is a reliable and generalizable predictive scale to identify patients at risk of difficult intravenous access.

Download Full-text

Validity of a New Prediction Model to Identify Patients at Risk for Obstructive Sleep Apnea Hypopnea Syndrome

Ear Nose & Throat Journal ◽

10.1177/0145561320986045 ◽

2021 ◽

pp. 014556132098604

Author(s):

Krongthong Tawaranurak ◽

Sinchai Kamolphiwong ◽

Suthon Sae-wong ◽

Sangsuree Vasupongayya ◽

Thossaporn Kamolphiwong ◽

...

Keyword(s):

At Risk ◽

Obstructive Sleep Apnea ◽

Sleep Apnea ◽

Prediction Model ◽

Epworth Sleepiness Scale ◽

Characteristic Analysis ◽

Data Set ◽

Obstructive Sleep ◽

Patients At Risk ◽

Hypopnea Syndrome

Objectives: To develop and validate a new clinical prediction model for screening patients at risk for obstructive sleep apnea–hypopnea syndrome (OSAHS). Methods: This study used 2 data sets to develop and validate the model. To build the model, the first data set comprised 892 patients who had diagnostic polysomnography (PSG); data were assessed by multivariate logistic regression analysis. To validate the new model, the second data set comprised 374 patients who were enrolled to undergo overnight PSG. Receiver operating characteristic analysis and all predictive parameters were validated. Results: In the model development phase, univariate analysis showed 6 parameters were significant for prediction apnea–hypopnea index ≥15 events/hour: male sex, choking or apnea, high blood pressure, neck circumference >16 inches (female) or 17 inches (male), waist circumference ≥80 (female) or 90 cm (male), and body mass index >25 kg/m2. Estimated coefficients showed an area under the curve of 0.753. In the model validation phase, the sensitivity and specificity were approximately 93% and 26%, respectively, for identifying OSAHS. Comparison with the Epworth Sleepiness Scale score of ≥10 and STOP-Bang score ≥3 showed sensitivity of 42.26% and 56.23%, respectively, for detecting patients at risk. Conclusions: This new prediction model gives a better result on identifying patients at risk for OSAHS than Epworth Sleepiness Scale and STOP-Bang in terms of sensitivity. Moreover, this model may play a role in clinical decision-making for a comprehensive sleep evaluation to prioritize patients for PSG.

Download Full-text

Predicting atrial fibrillation after acute abdominal surgery

European Heart Journal ◽

10.1093/eurheartj/ehab724.2795 ◽

2021 ◽

Vol 42 (Supplement_1) ◽

Author(s):

C V Madsen ◽

B Leerhoey ◽

L Joergensen ◽

C S Meyhoff ◽

A Sajadieh ◽

...

Keyword(s):

Diabetes Mellitus ◽

Risk Factors ◽

Atrial Fibrillation ◽

Chronic Kidney Disease ◽

At Risk ◽

Kidney Disease ◽

Abdominal Surgery ◽

Prediction Model ◽

Vital Signs ◽

Patients At Risk

Abstract Introduction Post-operative atrial fibrillation (POAF) is currently considered a phenomenon rather than a definite diagnosis. Nevertheless, POAF is associated with an increased rate of complications, including stroke and mortality. The incidence of POAF in acute abdominal surgery has not been reported and prediction of patients at risk has not previously been attempted. Purpose We aim to report the incidence of POAF after acute abdominal surgery and provide a POAF prediction model based on pre-surgery risk-factors. Methods Designed as a prospective, single-centre, cohort study of unselected adult patients referred for acute, general, abdominal surgery. Consecutive patients (>16 years) were included during a three month period. No exclusion criteria were applied. Follow-up was based on chart reviews, including medical history, vital signs, blood samples and electrocardiograms. Chart reviews were performed prior to surgery, at discharge, and three months after surgery. Atrial fibrillation was diagnosed either by specialists in Cardiology or Anaesthesiology on ECG or cardiac rhythm monitoring (≥30 seconds duration). Multiple logistic regression with backward stepwise selection was used for model development. Receiver operating characteristic curves (ROC) including area under the curve (AUC) was produced. The study was approved by the Regional Ethics committee (H-19033464) and comply with the principles of the Declaration of Helsinki of the World Medical Association. Results In total, 466 patients were included. Mean (±SD) age was 51.2 (20.5), 194 (41.6%) were female, and cardiovascular comorbidity was present in ≈10% of patients. Overall incidence of POAF was 5.8% (27/466) and no cases were observed in patients <60 years. Incidence was 15.7% (27/172) for patients ≥60 years. Prolonged hospitalization and death were observed in 40.7% of patients with POAF vs 8.4% patients without POAF (p<0.001). Significant age-adjusted risk-factors were previous atrial fibrillation odds ratio (OR) 6.84 [2.73; 17.18] (p<0.001), known diabetes mellitus OR 3.49 [1.40; 8.69] (p=0.007), and chronic kidney disease OR 3.03 [1.20; 7.65] (p=0.019). A prediction model, based on age, previous atrial fibrillation, diabetes mellitus and chronic kidney disease was produced (Figure 1), and ROC analysis displayed AUC 88.26% (Figure 2). Conclusions A simple risk-stratification model as the one provided, can aid clinicians in identifying those patients at risk of developing POAF in relation to acute abdominal surgery. This is important, as patients developing POAF are more likely to experience complications, such as prolonged hospitalization and death. Closer monitoring of heart rhythm and vital signs should be considered in at-risk patients older than 60 years. Model validation is warranted. FUNDunding Acknowledgement Type of funding sources: None.

Download Full-text

Clinically useful prediction of hospital admissions in an older population

10.21203/rs.2.18154/v3 ◽

2020 ◽

Author(s):

Jan Marcusson ◽

Magnus Nord ◽

Huan-Ji Dong ◽

Johan Lyth

Keyword(s):

At Risk ◽

Prediction Model ◽

Older Persons ◽

Hospital Admissions ◽

Model Fitting ◽

Forward Selection ◽

Healthcare Data ◽

Patients At Risk ◽

Predicted Values ◽

Unplanned Hospital Admissions

Abstract Background: The healthcare for older adults is insufficient in many countries, not designed to meet their needs and is often described as disorganized and reactive. Prediction of older persons at risk of admission to hospital may be one important way for the future healthcare system to act proactively when meeting increasing needs for care. Therefore, we wanted to develop and test a clinically useful model for predicting hospital admissions of older persons based on routine healthcare data. Methods : We used the healthcare data on 40,728 persons, 75-109 years of age to predict hospital in-ward care in a prospective cohort. Multivariable logistic regression was used to identify significant factors predictive of unplanned hospital admission. Model fitting was accomplished using forward selection. The accuracy of the prediction model was expressed as area under the receiver operating characteristic (ROC) curve, AUC. Results: The prediction model consisting of 38 variables exhibited a good discriminative accuracy for unplanned hospital admissions over the following 12 months (AUC 0·69 [95% confidence interval, CI 0·68–0·70]) and was validated on external datasets. Clinically relevant proportions of predicted cases of 40 or 45% resulted in sensitivities of 62 and 66%, respectively. The corresponding positive predicted values (PPV) was 31% and 29%, respectively. Conclusion : A prediction model based on routine administrative healthcare data from older persons can be used to find patients at risk of admission to hospital. Identifying the risk population can enable proactive intervention for older patients with as-yet unknown needs for healthcare.

Download Full-text

Clinically useful prediction of hospital admissions in an older population

10.21203/rs.2.18154/v1 ◽

2019 ◽

Author(s):

Jan Marcusson ◽

Magnus Nord ◽

Huan-Ji Dong ◽

Johan Lyth

Keyword(s):

Health Care ◽

At Risk ◽

Prediction Model ◽

Older Persons ◽

Hospital Admissions ◽

Model Fitting ◽

Forward Selection ◽

Future Health ◽

Health Care Data ◽

Patients At Risk

Abstract Background The health care for older adults is insufficient in many countries, not designed to meet their needs and is often described as disorganized and reactive. Prediction of older persons at risk of admission to hospital may be one important way for the future health-care system to act proactively when meeting increasing needs for care. Therefore, we wanted to develop and test a clinically useful model for predicting hospital admissions of older persons based on routine health-care data.Methods We used the health-care data on 40,728 persons, 75-109 years of age to predict hospital in-ward care in a prospective cohort. Multivariable logistic regression was used to identify significant factors predictive of unplanned hospital admission. Model fitting was accomplished using forward selection. The accuracy of the prediction model was expressed as area under the receiver operating characteristic (ROC) curve, AUC.Results The prediction model consisting of 38 variables exhibited a good discriminative accuracy for unplanned hospital admissions over the following 12 months (AUC 0·69 [95% confidence interval, CI 0·68–0·70]) and was validated on external datasets. Clinically relevant proportions of predicted cases of 40 or 45% resulted in sensitivities of 62 and 66%, respectively. The corresponding positive predicted values (PPV) was 31% and 29%, respectively.Conclusion A prediction model based on routine administrative health-care data from older persons can be used to find patients at risk of admission to hospital. Identifying the risk population can enable proactive intervention for older patients with as-yet unknown needs for health care.

Download Full-text

Deep learning detects heart failure with preserved ejection fraction using a baseline electrocardiogram

European Heart Journal - Digital Health ◽

10.1093/ehjdh/ztab081 ◽

2021 ◽

Author(s):

Matthias Unterhuber ◽

Karl-Philipp Rommel ◽

Karl-Patrik Kresoja ◽

Julia Lurz ◽

Jelena Kornej ◽

...

Keyword(s):

Heart Failure ◽

At Risk ◽

Deep Learning ◽

Ejection Fraction ◽

Predictive Value ◽

Validation Cohort ◽

External Validation ◽

Preserved Ejection Fraction ◽

Derivation Cohort ◽

Patients At Risk

Abstract Background Heart failure with preserved ejection fraction (HFpEF) is a rapidly growing global health problem. To date, diagnosis of HFpEF is based on clinical, invasive and laboratory examinations. Electrocardiographic findings may vary, and there are no known typical ECG features for HFpEF. Methods This study included two patient cohorts. In the derivation cohort, we included n = 1884 patients who presented with exertional dyspnea or equivalent and preserved ejection fraction (≥50%) and clinical suspicion for coronary artery disease. The ECGs were divided in segments, yielding a total of 77.558 samples. We trained a convolutional neural network (CNN) to classify HFpEF and control patients according to ESC criteria. An external group of 203 volunteers in a prospective heart failure screening program served as validation cohort of the CNN. Results The external validation of the CNN yielded an AUC of 0.80 (95% CI 0.74–0.86) for detection of HFpEF according to ESC criteria, with a sensitivity of 0.99 (CI 0.98–0.99) and a specificity of 0.60 (95% CI 0.56–0.64), with a positive predictive value of 0.68 (95%CI 0.64–0.72) and a negative predictive value of 0.98 (95% CI 0.95–0.99). Conclusion In this study, we report the first deep learning-enabled CNN for identifying patients with HFpEF according to ESC criteria including NT-proBNP measurements in the diagnostic algorithm among patients at risk. The suitability of the CNN was validated on an external validation cohort of patients at risk for developing heart failure, showing a convincing screening performance.

Download Full-text